We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics in each region by Gauss-Markov models, and infer the model parameters as well as the boundary of the regions in a variational optimization framework. Numerical results demonstrate that - in contrast to purely texture-based segmentation schemes - our method is effective in segmenting regions that differ in their dynamics even when spatial statistics are identical.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dynamic texture segmentation


    Contributors:
    Doretto, (author) / Cremers, (author) / Favaro, (author) / Soatto, (author)


    Publication date :

    2003-01-01


    Size :

    608505 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Dynamic Texture Segmentation

    Doretto, G. / Cremers, D. / Favaro, P. et al. | British Library Conference Proceedings | 2003


    Quaternion color texture segmentation

    Shi, L. / Funt, B. | British Library Online Contents | 2007


    Dynamic texture segmentation based on deterministic partially self-avoiding walks

    Gonçalves, W. N. / Bruno, O. M. | British Library Online Contents | 2013


    Image Segmentation by Texture Analysis

    Di Ruberto, C. / Rodriguez, G. / Vitulano, S. et al. | British Library Conference Proceedings | 1999


    Nested partitions using texture segmentation

    Lakshmanan, V. / DeBrunner, V.E. / Rabin, R. | IEEE | 2002